© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71374
    Prev
    Next
    INDEX
    Explanations

    lucid sex, binary systems, tracker, dynamic test, street light

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     distante
    0.48
    doesn
    0.48
     palpable
    0.46
    distant
    0.45
     Poche
    0.45
    
    0.43
    langan
    0.42
     shuffled
    0.42
     shameful
    0.41
     還
    0.41
    POSITIVE LOGITS
     பெயர்
    0.51
     Hinton
    0.45
    愷
    0.45
     organik
    0.44
    ாவை
    0.43
    ogenic
    0.43
    ointers
    0.43
     Henrique
    0.42
    ella
    0.42
    క్
    0.42
    Activations Density 0.000%

    No Known Activations